Does Higher Order LSTM Have Better Accuracy for Segmenting and Labeling Sequence Data?

TL;DR

This paper introduces a high order LSTM model and a multi-order BiLSTM approach that effectively incorporate longer-distance tag dependencies, achieving state-of-the-art results in sequence labeling tasks.

Contribution

The authors propose a novel high order LSTM and a scalable multi-order BiLSTM model that captures longer-range tag dependencies without complex computations.

Findings

MO-BiLSTM achieves state-of-the-art in chunking

High order LSTM improves label dependency modeling

Scalable approach maintains efficiency with pruning

Abstract

Existing neural models usually predict the tag of the current token independent of the neighboring tags. The popular LSTM-CRF model considers the tag dependencies between every two consecutive tags. However, it is hard for existing neural models to take longer distance dependencies of tags into consideration. The scalability is mainly limited by the complex model structures and the cost of dynamic programming during training. In our work, we first design a new model called "high order LSTM" to predict multiple tags for the current token which contains not only the current tag but also the previous several tags. We call the number of tags in one prediction as "order". Then we propose a new method called Multi-Order BiLSTM (MO-BiLSTM) which combines low order and high order LSTMs together. MO-BiLSTM keeps the scalability to high order models with a pruning technique. We evaluate MO-BiLSTM on all-phrase chunking and NER datasets. Experiment results show that MO-BiLSTM achieves the state-of-the-art result in chunking and highly competitive results in two NER datasets.